© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119478
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     any
    -0.08
     Any
    -0.07
     very
    -0.06
    任何
    -0.06
    ordin
    -0.06
     Very
    -0.06
    Any
    -0.06
     herhangi
    -0.06
    任意
    -0.06
     mus
    -0.06
    POSITIVE LOGITS
     기다
    0.06
     purchased
    0.06
     今
    0.06
     сейчас
    0.06
     compétence
    0.06
    íu
    0.06
     purchases
    0.05
    ček
    0.05
     ahora
    0.05
    isPartOf
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.